RLXBT evidence report and strategy research canvas
Free evidence check · no signup

Is your trading edge real?

Give RLXBT market data. It generates testable strategies, includes trading costs, and tries to break every result out of sample — before you risk money on it.

Real BTC data included · Result in about 20 seconds · No credit card

Local-first dataRust execution engineMac or Docker

Real evidence verdict

BTCUSDT · 1h · 4,999 bars

No edge

Hypotheses tested

12

Rejected

10

OOS windows positive

67%

Monte Carlo p5

−23.97%

Why it failed

The best in-sample result degraded out of sample. Monte Carlo downside remained too large to promote it.

A rejected strategy is a useful result: it is one less false edge to deploy.

One job

Try to falsify the strategy.

RLXBT does not promise profitable signals. It gives your idea a reproducible test and shows exactly where the evidence holds or breaks.

01

Generate bounded ideas

Start from simple, inspectable hypotheses instead of an AI story that cannot be reproduced.

02

Include real friction

Run the event-driven Rust engine with fees, slippage, realistic fills and enough trades to matter.

03

Attack the survivor

Use out-of-sample windows, Monte Carlo and sensitivity tests to expose fragile or overfit results.

Same engine · your server

Activate once. Keep your research agent online 24/7.

Deploy the hardened RLXBT image with Docker Compose on Ubuntu x86_64 or ARM64. Enter your license key, connect your agent to the private endpoint, and keep researching without a desktop session.

  • Same backtest and validation path as the desktop engine
  • One license activation tied to the server, preserved across container updates
  • No Python runtime and no strategy data sent to RLXBT cloud
  • Private MCP/HTTP endpoint for Claude, Cursor, Codex or your own agent
ubuntu · docker compose

$ docker compose up -d

license activated for this server

engine healthy on 127.0.0.1:8142

agentbacktestreject overfit

agentwalk_forwardevidence report

Choose by outcome

Explore free. Pay when you need proof.

Explore

Free

Test the workflow on your data and discover candidates.

  • ✓ Online evidence check without signup
  • ✓ Local engine up to 10K bars
  • ✓ Mac and Docker activation
Run a free test

Prove

Pro

$49/month

Attack overfitting before you deploy a strategy.

  • ✓ Unlimited bars and backtests
  • ✓ Walk-Forward, Monte Carlo and sensitivity
  • ✓ Mac or 24/7 Docker server
See Pro evidence suite →

Questions

What you need to know

Find the false edge before the market does.

Start with a real BTC dataset. No account, no configuration, and no promise that the answer will be comfortable.